You will get Custom YOLOv8 invoice data extraction model in Python
Project details
You will get a YOLOv8 model that detects and extracts 14 fields
from invoice images — vendor name, invoice number, dates, line
items, totals, tax, PO number, and more.
VALIDATED PERFORMANCE (100 test invoices):
• mAP50: 0.907 overall
• line_items_block: 0.994 | total_due: 0.911
• Inference: 6ms per image
WHAT YOU GET:
→ Model weights (.pt + .onnx)
→ Python inference script (image → JSON output)
→ FastAPI REST endpoint (ready to deploy)
→ README with setup instructions
Trained on 900+ annotated invoices, 100 epochs, Tesla T4 GPU.
Message me before ordering — I'll confirm the model works
for your invoice format first.
from invoice images — vendor name, invoice number, dates, line
items, totals, tax, PO number, and more.
VALIDATED PERFORMANCE (100 test invoices):
• mAP50: 0.907 overall
• line_items_block: 0.994 | total_due: 0.911
• Inference: 6ms per image
WHAT YOU GET:
→ Model weights (.pt + .onnx)
→ Python inference script (image → JSON output)
→ FastAPI REST endpoint (ready to deploy)
→ README with setup instructions
Trained on 900+ annotated invoices, 100 epochs, Tesla T4 GPU.
Message me before ordering — I'll confirm the model works
for your invoice format first.
Machine Learning Tools
NumPy, OpenCV, pandas, Python, PyTorch, TensorFlow, Tesseract OCRWhat's included
| Service Tiers |
Starter
$150
|
Standard
$300
|
Advanced
$500
|
|---|---|---|---|
| Delivery Time | 3 days | 5 days | 7 days |
Number of Revisions | 1 | 2 | 3 |
Number of Model Variations | 1 | 1 | 2 |
Number of Scenarios | 1 | 2 | 3 |
Number of Graphs/Charts | 1 | 2 | 3 |
Model Validation/Testing | |||
Model Documentation | - | ||
Data Source Connectivity | - | ||
Source Code |
Optional add-ons
You can add these on the next page.
Fast Delivery
+$50
Additional Revision
+$30
Additional Model Variation
(+ 1 Day)
+$100
Data Source Connectivity
(+ 1 Day)
+$80About Marek
Business Automation & Computer Vision Engineer | Invoice AI YOLOv8
Gdansk, Poland - 10:01 am local time
What I deliver:
— Invoice & document extraction (YOLOv8 + OCR, structured JSON output, 95%+ accuracy)
— Business process automation (Python, n8n, Make, API integrations)
— Computer vision systems (defect detection, object counting, real-time camera analysis)
Every project I deliver is production-ready, documented, and built to scale. I don't disappear after handoff.
Currently available for fixed-price projects and retainers. Message me with your bottleneck — most projects scope out in one conversation.
Steps for completing your project
After purchasing the project, send requirements so Marek can start the project.
Delivery time starts when Marek receives requirements from you.
Marek works on your project following the steps below.
Revisions may occur after the delivery date.
Dataset validation & field mapping
I review your sample invoices and confirm which of the 14 fields the model will detect. I'll notify you if any custom classes are needed.
Model training & evaluation
: YOLOv8 trained on 900+ annotated invoices. I share validation metrics (mAP50, per-class accuracy) before delivery.